© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3847
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating superiority or excellence

    oai_token-act-pair · gpt-3.5-turbo

    comparisons indicating superiority or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uto
    -0.74
    urther
    -0.71
    ALE
    -0.68
    ERN
    -0.65
    eeper
    -0.65
    ensor
    -0.64
    iosyn
    -0.64
    ango
    -0.64
    uria
    -0.64
    imb
    -0.63
    POSITIVE LOGITS
     anybody
    0.83
     anything
    0.83
     anyone
    0.80
     ever
    0.80
     usual
    0.79
     useless
    0.76
     ours
    0.73
     average
    0.71
     placebo
    0.71
    average
    0.71
    Activations Density 0.091%

    No Known Activations